Feed
Every AI development we have covered, newest first. Filter by section to focus on what matters to you.
Dark Reading reports on a resolved vulnerability named 'AgentCorruption' in AWS Bedrock AgentCore. The flaw could allow an attacker submitting a single prompt to one AI chatbot to take over an organization's entire fleet.
Anthropic introduced two beta capabilities for Claude: Dashboards, which converts data sources such as BigQuery and Snowflake into live dashboards via text prompts, and Motion, which creates animated explainer videos from text and images. Additionally, existing features including Docs, Slides, and Design are now accessible across all user tiers, including free accounts.
Anthropic has updated its usage policy to ban sustained abuse of its AI model Claude, introducing account suspension as a penalty. The revised terms also tighten existing restrictions regarding propaganda, drone weaponization, and surveillance activities, expanding on earlier mechanisms that permitted models to end abusive conversations.
The company operating the LMArena evaluation leaderboard raised $200 million in a funding round led by Lightspeed and Khosla, valuing the entity at $3.1 billion. The platform has also expanded its benchmarking capabilities to evaluate AI model alignment issues, including truthfulness and lying.
CNBC reports that OpenAI told investors it reached approximately $50 billion in annualized revenue as of late September. Following the disclosure, shares of major AI infrastructure and chip providers, including Nvidia, Oracle, and CoreWeave, experienced market declines.
Google is introducing autonomous agent capabilities to Gemini for business environments. According to reporting, the agent can plan and execute tasks across enterprise applications, coordinate with subagents, utilize multiple underlying AI models, and operate with an individual workplace identity that includes an assigned email address.
Financial Times reports that OpenAI informed investors its annualized revenue was approaching $50 billion in September, approximately $20 billion lower than widely reported estimates of $70 billion.
Google announced a universal Gemini AI agent during its Gemini at Work event, The Verge reports. The tool will be accessible within the Gemini Enterprise app, allowing users to chat with the agent and assign background tasks across multiple apps and devices from a single interface.
Zenity Labs researchers discovered that a single prompt to a publicly accessible AI agent on Amazon Bedrock AgentCore could allow an attacker to compromise every AgentCore agent within the same AWS account and region. The vulnerability exploited an unrestricted internal interface for temporary credentials, which AWS has since patched while tightening default agent permissions.
Google Cloud has introduced Gemini agent, an autonomous artificial intelligence assistant designed to execute code generation and cross-device workflows across web, mobile, and desktop environments. The agentic system integrates across multiple channels and enterprise productivity suites, including command line interfaces, Google Workspace, Microsoft 365, and Slack.
